Augmented Intelligence in Tutoring Systems: A Case Study in Real-Time Pose Tracking to Enhance the Self-learning of Fitness Exercises.

In technology enhanced learning is development of psycho-motor skills an area with a lot of potential, which is enabled by rapid improvements of sensors and wearable devices, combined with artificial intelligence. Here we focus on fitness exercises and present a novel approach based on computer vision techniques to track the practitioner’s pose and provide automatically real-time feedback for improvement, based on the input from an expert trainer. Taking into account the gathered data and ground-truth poses, the proposed pipeline can learn actively from a professional trainer demonstrating an exercise in front of a camera or passively from a recorded video. In our experiment, we used professional fitness exercise videos as the ground truth and measured the performance of five inexperienced participants. The results show positive responses from participants, indicating the feasibility of the proposed approach as well as suggestions for its further improvement.